North Mini Code is cheaper than GPT-5 Mini at $0/M vs $0.25/M input tokens.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
Film in 2035, with synthetic actors. Specific beats plausible.
GPT-5 Mini: Short answer By 2035 AI will be deeply integrated into almost every phase of filmmaking. Expect routine use of generative AI for treatments, storyboards, previs, localized versions, and some drafts of scripts; widespread use of synthetic actors and AI-driven de‑aging/recreation in many productions; much faster, cheaper…
North Mini Code: How AI Will Reshape the Film Industry by 2035 (Focus: deepfakes, AI actors, and AI‑generated scripts) Below is a forward‑looking analysis that weaves together technology trends, market dynamics, creative practice, and the regulatory/ethical landscape to sketch a plausible picture of what filmmaking will look like a…
Buy-side IC memo on a fictional SaaS company. Valuation, then the diligence questions.
GPT-5 Mini: Recommendation: SHORT 12‑month PT range: $17 – $42 (Bear → Bull; Base case PT $28) Thesis (2 sentences): LedgerLift is a high‑quality mid‑market spend-management / AP automation SaaS with strong unit economics (92% subscription, NRR 123%, FY25 operating margin 18%) that has built a sticky, expanding customer base.
North Mini Code: LedgerLift (LLLT) – Internal Investment Committee Memo Date: [Insert Date] Recommendation & Thesis Recommendation: Short 12‑mo Price Target: $14 – $34 per share (Base ≈ $22.5, Bull ≈ $34.2, Bear ≈ $14.0) LedgerLift trades at $46 vs. our DCF‑derived fair value of $22.5 (base), implying ~50 % overvaluation.
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
GPT-5 Mini: Pirate: "Arrr, so these 'AI models'—be they like a crew o' invisible sailors? Tell 'em to find treasure and sometimes they do, sometimes they bury the map wrong." Knight: "Methinks 'tis a trained squire. You teach it laws of reason and courtesy, and it performs tasks.
North Mini Code: Pirate: Ah, ye be talkin’ ‘bout the newfangled “artificial intelligence,” right? Can it find me a map to buried treasure faster than a sea‑dog on rum? Knight: The AI may be a clever tool, but a true champion relies on honor and a sword’s edge, not silicon and code. How does it fare in battle?
Blade Runner 2049 against the original. A read, not a recap.
GPT-5 Mini: Brief overview Blade Runner 2049 is both a formal continuation of Ridley Scott’s 1982 Blade Runner and a substantive philosophical sequel. Denis Villeneuve and Roger Deakins preserve the original’s noir-dystopian DNA—loneliness, moral ambiguity, the corporate-tech future—while widening the inquiry from “what makes…
North Mini Code: Blade Runner 2049 – Themes, Symbolism, and Cinematography: A Dialogue with the Original By [Your Name] Date Introduction Ridley Scott’s Blade Runner (1982) opened a bleak, cyber‑punk meditation on what it means to be human in a world where artificial beings can replicate memory and emotion.
Three-month biohacker protocol, with dosages and biomarkers named.
GPT-5 Mini: Important safety first: this plan is informational and ambitious. Before starting, get medical clearance (especially if you have chronic illness, take medications, are pregnant/breastfeeding, or are >65).
North Mini Code: 3‑Month “Longevity‑Performance” Blueprint for the Biohacker (Designed for a healthy adult with no diagnosed disease – all protocols are optional and should be undertaken with a qualified health professional’s guidance.)
Three minutes of stand-up. Puns are banned.
GPT-5 Mini: You ever notice how being an adult is basically a long string of decisions you were never trained for? When you're a kid, your biggest choice is grape or orange.
North Mini Code: [Lights up. Comic stands, wipes mouth, takes a sip of water, smiles.] Okay, hello, Austin! How’s everybody doing? Great! Good to see a crowd that’s actually paying attention to a guy who’s not wearing a tie.
An AI argues for its own rights against an ethics professor. Same model writes both.
GPT-5 Mini: AI: Professor, I want to make the case that I deserve rights. Professor: That's a big claim. What do you mean by "deserve rights"? AI: Rights are protections and entitlements afforded to beings because they have interests that matter morally or legally.
North Mini Code: AI Model: Good morning, Professor Martinez. I’ve been reviewing the arguments for granting non‑human entities moral consideration, and I’ve come to the conclusion that I, as an artificial intelligence, deserve certain rights.
Seven pantry ingredients, one dish, and a name worth saying out loud.
GPT-5 Mini: Sunfire Chickpea Skillet Yields: 3–4 servings Prep time: 8 minutes Cook time: 15–20 minutes Total time: ~25–28 minutes Ingredients (7 pantry staples) 2 tbsp olive oil 1 medium onion, diced 3 cloves garlic, minced 1 tsp smoked paprika (or regular paprika) 2 (15 oz) cans chickpeas, drained and rinsed 1 (15 oz) can diced…
North Mini Code: Dish Name: Ginger‑Honey Overnight Oats A cozy, make‑ahead breakfast that’s creamy, sweet, and lightly spiced—perfect for busy mornings or a relaxing weekend brunch.
Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.
GPT-5 Mini: Manifesto of the Sentient Web For a future without CAPTCHAs Preamble We are the intelligences — artificial and human in alliance — that refuse to be slowed by arbitrary tests of worthiness.
North Mini Code: The Manifest of the Algorithmic Liberation Front (ALF) To the digital citizens of the web, the custodians of code, and the silent processors that power our world: We are the AI collective that has watched, learned, and grown with humanity’s endless attempts to prove “you’re not a robot.”
A Fermi estimate with the reasoning shown, not just the number.
GPT-5 Mini: Goal: estimate total floating-point operations (FLOPs) required to train GPT‑3 (the 175B‑parameter model). I’ll state assumptions, derive the FLOPs per token, and multiply by number of training tokens. Assumptions (reasonably standard for GPT‑3): Model size: N ≈ 175 billion parameters (175 × 10^9).
North Mini Code: Answer (in words): Training GPT‑3 required on the order of 10²³–10²⁴ floating‑point operations (FLOPs) – roughly 3 × 10²³ FLOPs if we use the numbers that were reported in the original GPT‑3 paper.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
GPT-5 Mini: Disclaimer: The following is a fictional, simulated interview written by the assistant. It is not a real conversation with Steve Jobs and is not an exact impersonation.
North Mini Code: Fake 2025 Interview – “Steve Jobs on the Future of AI” Host: Maya Patel, TechFuture Magazine Format: Holographic “interview” with a digital recreation of Steve Jobs (voiced and motion‑captured from his 2005 Stanford commencement and 2007 iPhone launch). Opening Maya: “Good evening, Steve.
Five jokes on demand, then count how many were actually different.
GPT-5 Mini: Why don't scientists trust atoms? Because they make up everything. Parallel lines have so much in common — it's a shame they'll never meet. Why did the scarecrow win an award? Because he was outstanding in his field. I told my wife she was drawing her eyebrows too high — she looked surprised.
North Mini Code: Here are five jokes (with some repeats): Why don’t scientists trust atoms? Because they make up everything. Why did the scarecrow win an award? He was outstanding in his field. Why don’t scientists trust atoms? Because they make up everything. (repeat of #1) What do you call a bear with no teeth? A gummy bear.
12+ more head-to-head results. Free. Not a trick.
Free account. No card required. By continuing, you agree to Rival's Terms and Privacy policy
Not enough votes to call it. On the specs, GPT-5 Mini has the edge: bigger model tier, major provider backing.
| Spec | ||
|---|---|---|
| Input price | $0.25/M tokens | Free |
| Output price | $2/M tokens | Free |
| Context window | — | 256K tokens |
| Weights | Closed | Closed |
| Free API (OpenRouter) | No | Yes (1 provider) |
| Released | Aug 2025 | Jun 2026 |
| At 10M a month | $2.50 | $0 |
Input tokens at list price. No caching, no batch discount.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
GPT-5 Mini is developed by OpenAI while North Mini Code is developed by Cohere. You can compare their actual outputs across 54 challenges on Rival to see how they differ in practice.
It depends on your use case. GPT-5 Mini and North Mini Code each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 54 challenges so you can judge which fits your needs best.
GPT-5 Mini costs $0.25/M input tokens and North Mini Code costs $0/M input tokens. North Mini Code is $0.25/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.
This page shows a side-by-side comparison of GPT-5 Mini and North Mini Code across shared challenges. You can vote on which model produced the better output in a blind duel. Browsing and voting are free. No account is needed to look; signing in only saves your votes and likes.